© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 58883
    Prev
    Next
    INDEX
    Explanations

    keywords associated with health, social issues, and moral dilemmas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    health reasons, insurance introduced, crime, alcohol

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ParallelGroup
    -0.88
    findpost
    -0.65
    IContainer
    -0.62
    новништво
    -0.61
    躇
    -0.59
    WithIdentifier
    -0.56
    CloseOperation
    -0.56
    viewDidLoad
    -0.56
    liceerd
    -0.56
    providedIn
    -0.54
    POSITIVE LOGITS
     ویکی‌پدی
    0.47
     pinulongan
    0.37
     funk
    0.30
    nmgp
    0.28
     meg
    0.27
     lago
    0.27
    Спасылкі
    0.27
     fireworks
    0.27
     gradu
    0.27
     nukes
    0.27
    Activations Density 0.046%

    No Known Activations